Systems and methods for detecting objectionable content in a social network
AssigneeLimited Liability Company Mail.Ru
InventorAndrey Stroganov
Life of this patent
Estimating the term…
Loading patent…
AssigneeLimited Liability Company Mail.Ru
InventorAndrey Stroganov
Estimating the term…
A method for detecting an objectionable material within a plurality of items of content comprising: determining a first number for each of the plurality of items of content representing user views of said each of the plurality of items of content; determining a second number for each of the plurality of items of content representing user likes or reposts of said each of the plurality of items of content; calculating a suspicion score for each of the plurality of items of content by dividing the corresponding first number by the corresponding second number; ranking the plurality of items of content based on the calculated suspicion score; providing the ranked plurality of items of content to an administrator; and receiving a feedback from the administrator, the feedback identifying the objectionable material within at least some of the plurality of items of content.
A computer-implemented method for detecting an objectionable material within a plurality of items of content, the method being performed in connection with a computerized system comprising a processing unit, a memory and a content storage, the method comprising:
A non-transitory computer-readable medium embodying a set of computer-readable instructions, which, when executed in connection with a computerized system comprising a processing unit, a memory and a content storage, cause the computerized system to perform a computer-implemented method for detecting an objectionable material within a plurality of items of content, the method comprising:
A computerized system comprising a processing unit, a memory and a content storage, the memory storing a set of computer-readable instructions, which, when executed by the processing unit, cause the computerized system to perform a computer-implemented method for detecting an objectionable material within a plurality of items of content, the method comprising:
Dependencies are inferred from the claim text.